Geomclip: Contrastive Geometry-text Pre-training For Molecules

Abstract

Pretraining molecular representations is crucial for drug and material discovery. Recent methods focus on learning representations from geometric structures, effectively capturing 3D position information. Yet, they overlook the rich information in biomedical texts, which detail molecules' properties and substructures. With this in mind, we set up a data collection effort for 200K pairs of ground-state geometric structures and biomedical texts, resulting in a PubChem3D dataset. Based on this dataset, we propose the GeomCLIP framework to enhance for multi-modal representation learning from molecular structures and biomedical text. During pre-training, we design two types of tasks, i.e., multimodal representation alignment and unimodal denoising pretraining, to align the 3D geometric encoder with textual information and, at the same time, preserve its original representation power. Experimental results show the effectiveness of GeomCLIP in various tasks such as molecular property predicti

Stats

• citations0
• S2 citations—
• github stars4
• HF likes0
• heat score1.40
• arxiv keyxiao2024geomclip

Related papers

• Thin Bridges For Drug Text Alignment: Lightweight Contrastive Learning For Target Specific Drug Retrieval (2025)0.00
• Bridging Text And Crystal Structures: Literature-driven Contrastive Learning For Materials Science (2025)3.58
• Medclip: Contrastive Learning From Unpaired Medical Images And Text (2022)26.02
• Advancing Myopia To Holism: Fully Contrastive Language-image Pre-training (2024)0.00
• Weakly Supervised Cross-modal Learning In High-content Screening (2023)2.26
• Aligning Proteins And Language: A Foundation Model For Protein Retrieval (2025)0.00
• Towards Cross-modal Text-molecule Retrieval With Better Modality Alignment (2024)4.52
• FG-CLIP: Fine-grained Visual And Textual Alignment (2025)5.75